Fish are indicative species with a relatively balanced ecosystem. Underwater target fish detection is of great significance to fishery resource investigations. Traditional investigation methods cannot meet the increasing requirements of environmental protection and investigation, and the existing target detection technology has few studies on the dynamic identification of underwater fish and small targets. To reduce environmental disturbances and solve the problems of many fish, dense, mutual occlusion and difficult detection of small targets, an improved CME-YOLOv5 network is proposed to detect fish in dense groups and small targets. First, the coordinate attention (CA) mechanism and cross-stage partial networks with 3 convolutions (C3) structure are fused into the C3CA module to replace the C3 module of the backbone in you only look once (YOLOv5) to improve the extraction of target feature information and detection accuracy. Second, the three detection layers are expanded to four, which enhances the model’s ability to capture information in different dimensions and improves detection performance. Finally, the efficient intersection over union (EIOU) loss function is used instead of the generalized intersection over union (GIOU) loss function to optimize the convergence rate and location accuracy. Based on the actual image data and a small number of datasets obtained online, the experimental results showed that the mean average precision (mAP@0.50) of the proposed algorithm reached 94.9%, which is 4.4 percentage points higher than that of the YOLOv5 algorithm, and the number of fish and small target detection performances was 24.6% higher. The results show that our proposed algorithm exhibits good detection performance when applied to densely spaced fish and small targets and can be used as an alternative or supplemental method for fishery resource investigation.

In this paper, based on the improved DeepSORT algorithm, four target species of passing fish (Schizothorax o’connori, Schizothorax waltoni, Oxygymnocypris stewartii and Schizopygopsis younghusbandi) from a fishway project in the middle reaches of the Y River were used to achieve dynamic identification and automatic counting of passing fish species using fishways monitoring video. This method used the YOLOv5 model as the target detection model. In view of the large deformation by fish body twisting, the network structure of the re-identification (ReID) model was deepened to strengthen the feature extraction ability of the model. It was proposed to identify and track fish that cross the line by setting a virtual baseline to achieve the dynamic identification of fish species passing and the automatic counting of upward and downward quantities. The results showed that 1) among the five models, YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x, the highest value of mean average precision (mAP) was 92.8% achieved by the YOLOv5x model. Specifically, recognition accuracies of 96.95%, 94.95%, 88.79%, and 91.93% were recorded for Schizothorax o’connori, S. waltoni, S. younghusbandi and O. stewartii, respectively. 2) The error rate of the improved ReID model was 20.3%, which was 20% lower than that before the improvement, making it easier for the model to obtain target features. 3) The average accuracy of the improved DeepSORT algorithm for counting four target fishes was 75.5%, among which the accuracy of Schizothorax o’connori, S. waltoni, S. younghusbandi and O. stewartii were 83.6%, 71.1%, 68.1%, and 79.3%, respectively. Meanwhile, the running speed was 44.6 fps, which met the real-time monitoring. This method is the first to implement intelligent identification of the target passing fish in fishways projects, which can accumulate long series monitoring data for fishways operation and management and provide a technical solution and reference for the work related to the realization of intelligent and informative passing fish monitoring.

Introduction: Changes in fish phenotypes during aquaculture must be monitored to improve the quality of fishery resources. Therefore, a method for segmenting and measuring phenotypes rapidly and accurately without harming the fish is essential. This study proposes an intelligent fish phenotype segmentation method based on the residual network, ResNet50, and atrous spatial pyramid pooling (ASPP).Methods: A sufficient number of fish phenotypic segmentation datasets rich in experimental research was constructed, and diverse semantic segmentation datasets were developed. ResNet50 was then built as the backbone feature extraction network to prevent the loss of fish phenotypic feature information and improve the precision of fish phenotypic segmentation. Finally, an ASPP module was designed to improve the phenotypic segmentation accuracy of different parts of fish.Results: The test algorithm based on the collected fish phenotype segmentation datasets showed that the proposed algorithm (RA-UNet) yielded the best results among several advanced semantic segmentation models. The mean intersection over union (mIoU) and mean pixel accuracy (mPA) were 87.8% and 92.3%, respectively.Discussion: Compared with the benchmark UNet algorithm, RA-UNet demonstrated improvements in the mIoU and mPA by 5.0 and 1.8 percentage points, respectively. Additionally, RA-UNet exhibited superior fish phenotype segmentation performance, with a low false detection rate and clear and complete edge segmentation. Conclusively, the RA-UNet proposed in this study has high accuracy and edge segmentation ability and can, therefore, directly improve the efficiency of phenotypic monitoring in fish farming.